Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
ec53d03
phi-2-kto-i0
/
runs
/
Sep28_17-12-29_gpu4-119-5
1 contributor
History:
1 commit
BraylonDash
Training in progress, step 860
a78f2fc
verified
about 1 month ago
events.out.tfevents.1727507596.gpu4-119-5.4011095.0
5.51 kB
LFS
Training in progress, step 860
about 1 month ago